isitcooked.ai
← leaderboard

DeepSeek V4 Flash

no data

DeepSeek · deepseek/deepseek-v4-flash

Daily test history (90 days, baseline band = trailing mean ± 2σ)

No daily test data yet.

Public benchmarks overall 69.4

MMLU-Pro

84

GPQA Diamond

76

SWE-bench Verified

63

LMArena Elo

1395

AIME 2025

85

retrieved 2026-07-02 from public sources — see methodology

Recent samples (latest run, one per test case)